Tibo's posts on August 16, 2026

Replying to @xikhar

@xikhar Banger

40 replies · 1 repost · 361 likes

Replying to @MarieAdant

@MarieAdant That you're missing a Codex sticker

60 replies · 1 repost · 422 likes

Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol. Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented. A larger context window lets Codex retain more code, tool output, and conversation history before summarizing older material. You need a model that supports it. And GPT-5.6 Sol, for example, has a documented 1,050,000-token window. Open ~/.codex/config.toml and add or update these settings at the top level, before any [section] headers: ``` model = "gpt-5.6-sol" model_context_window = 1000000 model_auto_compact_token_limit = 900000 ``` The first setting selects the model. The second tells Codex to use a one-million-token context budget. The third starts automatic history compaction around 900,000 tokens, leaving some headroom. Restart Codex client and start a new session after saving. To try the configuration for a single CLI session without changing your defaults: ``` codex -m gpt-5.6-sol \ -c model_context_window=1000000 \ -c model_auto_compact_token_limit=900000 ``` Have fun, but also know that we tuned the default carefully!

996 replies · 1,153 reposts · 14,626 likes

Sunday is for good vibes. As is any day of the week, but especially Sunday.

646 replies · 81 reposts · 4,657 likes

Replying to @Robertg761_

@Robertg761_ Indeed

28 replies · 0 reposts · 182 likes

Replying to @Ananth7e

@Ananth7e Maybe

156 replies · 13 reposts · 2,339 likes

Replying to @Ananth7e

@Ananth7e Maybe

100 replies · 2 reposts · 914 likes

Replying to @NotiDivad

@NotiDivad Yes

93 replies · 7 reposts · 1,378 likes

What's your /goal for the night?

2,468 replies · 45 reposts · 2,815 likes

Replying to @Ethan_Smartsys

@Ethan_Smartsys Happens to the best

25 replies · 1 repost · 156 likes

Replying to @butter86396

@butter86396 Sorry, only 11pm over here.

13 replies · 0 reposts · 408 likes

On tokens and prices per token. I said I’d write more about this, so here goes: an OpenAI token != another model’s token. We compare AI prices in dollars per million tokens as if a token were a standardized unit, like a gram or a kilowatt-hour. It isn’t. Different models use and produce the exact same text using different numbers of tokens, which means a lower price per token does not necessarily mean a lower bill. Imagine two identical pizzas. One is cut into 8 slices at $2 each. The other is cut into 16 slices at $1.25 each. The second place advertises cheaper slices, but the whole pizza costs $20 instead of $16. Bummer ... your stomach doesn't actually care about the number of slices you just ate. I know you are hungry now, but back to tokens. In one small comparison spanning English, technical, multilingual, and numerical text, the tokenizer we use for GPT-5.6 Sol used 766 tokens versus an estimated 1,170 for Claude Opus 5. That's a very significant difference of about 34.5% fewer tokens. You can get the same exact text, but pay for all those extra tokens. The price per token doesn't really tell this story. Even correcting for tokenizer differences misses the bigger point. What actually matters is price per successful outcome, and for that you can use benchmarks as a starting point, but really you have to try it and measure on your own use cases. That's all. May the tokens flow.

832 replies · 337 reposts · 6,892 likes

Replying to @RJMcGirr

@RJMcGirr Sol can probably migrate you in a few hours. Why isn't it worth the many $$$ you would get back in return?

15 replies · 0 reposts · 198 likes

Replying to @gusfeliciano

@gusfeliciano We have ZDR, tell me more

10 replies · 1 repost · 197 likes

Replying to @thsottiaux

@ns123abc I'll write more extensively about this, but OpenAI token != A\ token. We use different tokenizers. And OpenAI's tokenizer is significantly more efficient. This is important given you pay per token over the API and in usage. The difference is ~30% in number of tokens, definitely https://t.co/RwDz5AdK1t

26 replies · 10 reposts · 252 likes

Replying to @SnoyIatK

@SnoyIatK Which partnership programs do we need?

28 replies · 2 reposts · 156 likes

Replying to @_hibana01

@_hibana01 Yes

3 replies · 0 reposts · 159 likes

Replying to @ns123abc

@ns123abc Talking about sticker price?

13 replies · 1 repost · 553 likes

Replying to @drgrandehead

@drgrandehead @nxc42 DM

5 replies · 0 reposts · 67 likes

Replying to @DustdrifterX

@DustdrifterX DM

3 replies · 0 reposts · 156 likes

Replying to @AbdoKerdawy

@AbdoKerdawy Sol supports 1M, tell me more?

145 replies · 5 reposts · 790 likes

Replying to @AISupplyGuy1

@AISupplyGuy1 Do you have evals? Quite surprising as I would expect for most things you would net out 40-50% cheaper per task with Sol. Can you share more?

41 replies · 1 repost · 404 likes

Replying to @nxc42

@nxc42 DM

5 replies · 0 reposts · 218 likes

If you have a company and still use Opus instead of Sol, why so? Does price not matter to you? What's something that would convince you to switch?

4,212 replies · 179 reposts · 9,064 likes